nlweb-goodmem

GoodMem integration for NLWeb.

GoodMem gives AI agents retrieval-augmented generation (RAG) memory. Store documents in a space and GoodMem chunks, embeds, and indexes them so your agent can pull back the most relevant passages on any question.

This package exposes the GoodMem API as a set of NLWeb-style operation classes. Each operation has a run(...) method that returns a JSON string, making them callable from any NLWeb handler or tool dispatcher.

Installation

pip install nlweb-goodmem

For local development:

pip install -e ".[dev]"

Quickstart

import json
import os

os.environ["GOODMEM_BASE_URL"] = "https://localhost:8080"
os.environ["GOODMEM_API_KEY"] = "gm_xxxxxxxxxxxxxxxxxxxxxxxx"
os.environ["GOODMEM_VERIFY_SSL"] = "false"  # self-signed local server

from nlweb_goodmem import (
    GoodMemCreateMemory,
    GoodMemCreateSpace,
    GoodMemListEmbedders,
    GoodMemRetrieveMemories,
)

embedders = json.loads(GoodMemListEmbedders().run())
embedder_id = embedders["embedders"][0]["embedderId"]

space = json.loads(
    GoodMemCreateSpace().run(name="quickstart", embedder_id=embedder_id)
)
space_id = space["spaceId"]

GoodMemCreateMemory().run(
    space_id=space_id,
    text_content="The capital of France is Paris.",
)

results = json.loads(
    GoodMemRetrieveMemories().run(
        query="What is the capital of France?",
        space_ids=space_id,
        max_results=3,
    )
)
print(results)

Every operation's run(...) returns a JSON string. On success the parsed object includes "success": true and operation-specific fields. On failure it includes "success": false and an "error" field.

Available operations

Operation Description
GoodMemListEmbedders List embedder models available on the server
GoodMemListSpaces List all spaces accessible to the API key
GoodMemGetSpace Fetch a space by ID
GoodMemCreateSpace Create a space (idempotent by name)
GoodMemUpdateSpace Update a space's name, labels, or public-read flag
GoodMemDeleteSpace Delete a space and all of its memories
GoodMemCreateMemory Store text or a file as a memory
GoodMemListMemories List memories in a space, with pagination and filters
GoodMemRetrieveMemories Semantic retrieval across one or more spaces
GoodMemGetMemory Fetch a memory by ID, with optional content
GoodMemDeleteMemory Delete a memory

Retrieval options

GoodMemRetrieveMemories accepts the following parameters in addition to query, space_ids, and max_results:

Parameter Type Description
metadata_filter str SQL-style JSONPath filter applied server-side to every space key. Example: CAST(val('$.category') AS TEXT) = 'feat'
wait_for_indexing bool Poll for results when none come back on the first call (default True)
max_wait_seconds float Polling budget (default 60.0)
poll_interval float Seconds between polls (default 5.0)
reranker_id str Reranker model to refine result ordering
llm_id str LLM that generates a contextual abstract reply
relevance_threshold float Minimum score (0-1) for inclusion
llm_temperature float Creativity (0-2) for the LLM post-processor
chronological_resort bool Reorder results by creation time

Environment variables

Variable Description
GOODMEM_BASE_URL Base URL of the GoodMem API server
GOODMEM_API_KEY API key sent as X-API-Key
GOODMEM_VERIFY_SSL Set to false to skip TLS verification (default true)

When the env vars are set, every operation constructor can be called with no arguments.

End-to-end example

examples/example_usage.py walks through three scenarios: persistent project context, a scribe and analyst pipeline, and metadata-driven retrieval. The answering step uses OpenAI; install with pip install nlweb-goodmem[examples] and set OPENAI_API_KEY before running.

python examples/example_usage.py

License

Apache License 2.0. See LICENSE.

Project links

Data verified by PyPI on May 22, 2026
Data provided by the project maintainers, verified at the time the release was uploaded to PyPI.

Key dates

PyPI data
Data sourced directly from PyPI's database.
  • Released:
Latest release

1 maintainer

PyPI data
Data sourced directly from PyPI's database.
Avatar for mohammed.khalid from gravatar.com mohammed.khalid

Credits

Author: GoodMem

GitHub Statistics

Data verified by PyPI on May 22, 2026
The GitHub source repository was provided by the project maintainers and verified by PyPI at the time of upload. Stars, forks, and open issues/PRs are derived from that repository and have not been independently verified.

License

Apache Software License

Requires

Python >=3.10

Provides Extra

dev examples

Classifiers

Report project as malware

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

nlweb_goodmem-0.1.0.tar.gz (17.7 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

nlweb_goodmem-0.1.0-py3-none-any.whl (23.3 kB view details)

Uploaded Python 3

File details

Details for the file nlweb_goodmem-0.1.0.tar.gz.

File metadata

  • Download URL: nlweb_goodmem-0.1.0.tar.gz
  • Upload date:
  • Size: 17.7 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.12

File hashes

Hashes for nlweb_goodmem-0.1.0.tar.gz
Algorithm Hash digest
SHA256 b0c24f1b1ffb2c2000c28b6e620498a0aaefc6918c8c1ce6c0d79c41dfe82e83
MD5 0a1eec6d3746c0657886647fb759bafd
BLAKE2b-256 f66c6525f0712e2664bab1d3ab6e6592f7e388fab87090381a353f1a794b72bb

See more details on using hashes here.

Provenance

The following attestation bundles were made for nlweb_goodmem-0.1.0.tar.gz:

Publisher: publish.yml on PAIR-Systems-Inc/goodmem_nlweb

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file nlweb_goodmem-0.1.0-py3-none-any.whl.

File metadata

  • Download URL: nlweb_goodmem-0.1.0-py3-none-any.whl
  • Upload date:
  • Size: 23.3 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.12

File hashes

Hashes for nlweb_goodmem-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 e7682e828c9da70d6dcaa2ec5184139a086736c1d749df34d8108eef168f3ccd
MD5 4f4b74f4c9ad2fa6bc24fa9b6cc762ae
BLAKE2b-256 ed5ade91e9a061d5b1c0c14f16fcadc2a02f80547cdf6b876bf9d21337f4fca6

See more details on using hashes here.

Provenance

The following attestation bundles were made for nlweb_goodmem-0.1.0-py3-none-any.whl:

Publisher: publish.yml on PAIR-Systems-Inc/goodmem_nlweb

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Release history Release notifications | RSS feed

This release

0.1.0 This release

2 files

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page